Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Jailbreaking Vision-Language Models Through the Visual Modality
Aharon Azulay, Jan Dubiński, Zhuoyun Li +2
The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision co…
cs.CV2026
Conditioned Activation Transport for T2I Safety Steering
Maciej Chrabąszcz, Aleksander Szymczyk, Jan Dubiński +3
Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inferenc…